Anxiety Prediction Model Based on Smartwatch Activity Data and Self-Reported Affect Scale in Adolescents
Keywords:
Mental Health, Smartwatch, Adolescents, Wearable Sensors, Affect ScaleAbstract
This study proposes an anxiety prediction model based on smartwatch activity data integrated with a self-reported affect scale in adolescents. Anxiety among adolescents is a growing public health concern, often underdetected due to subjective assessment and limited continuous monitoring. To address this gap, this research combines objective physiological and behavioral indicators collected from smartwatches, including heart rate variability, sleep duration, physical activity intensity, and daily movement patterns, with subjective emotional states measured through a validated affect scale. Data were collected longitudinally from adolescent participants over several weeks to capture temporal variations in activity and mood. Machine learning techniques were applied to develop and evaluate predictive models capable of identifying anxiety levels with high accuracy. Model performance was assessed using standard metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that the integration of wearable sensor data with self-reported affect significantly improves anxiety prediction compared to single-source data models. The proposed model offers a scalable, non-invasive, and real-time approach for early anxiety detection, supporting timely intervention and personalized mental health monitoring for adolescents. This study contributes to the development of human-centered digital health technologies and highlights the potential of wearable-based analytics in preventive mental healthcare systems for future applications.
References
[1] L. Lutz, P. Veltmann, R. Meisterhans, and M. Giurgiu, “Associations between wearables vital parameters and self-perceived mood an ecological momentary assessment study among healthy adolescents,” Frontiers in Psychology, vol. 16, p. 1623886, 2025.
[2] Department of Health and Social Care, “Mental health and wellbeing plan: Discussion paper and call for evidence,” Department of Health and Social Care, United Kingdom, Tech. Rep., Apr 2022. [Online]. Available: https://www.gov.uk/government/calls-for-evidence/mental-health-and-wellbeing-plan-discussion-paper-and-call-for-evidence/mental-health-and-wellbeing-plan-discussion-paper
[3] U. Rahardja, L. Sulistyo, D. Safarina, M. R. Kusuma, N. Silawati, and Z. Nanle, “Hibahqu education monitoring platform based on human-centric orange technology laravel 12 vue. js,” ADI Bisnis Digital Interdisiplin Jurnal, vol. 6, no. 2, pp. 203–218, 2025.
[4] Y. T. Jo, S. W. Lee, S. Park, and J. Lee, “Association between heart rate variability metrics from a smartwatch and self-reported depression and anxiety symptoms: a four-week longitudinal study,” Frontiers in Psychiatry, vol. 15, p. 1371946, 2024.
[5] B. Saylam and O. D. ¨ ˙Incel, “Quantifying digital biomarkers for well-being: stress, anxiety, positive and negative affect via wearable devices and their time-based predictions,” Sensors, vol. 23, no. 21, p. 8987, 2023.
[6] K. Diantoro, M. P. Hannah, M. Wali, I. Sutedja, N. Silawati et al., “Optimizing federated learning efficiency for real-time online course applications,” in 2025 4th International Conference on Creative Communication and Innovative Technology (ICCIT). IEEE, 2025, pp. 1–7.
[7] E. Zhang, M. Clark, and A. Doryab, “Predicting the severity of anxiety in adolescents through passively sensed behaviors,” in Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies, 2025, pp. 81–92.
[8] Y.-B. Shin, A. Y. Kim, S. Kim, M.-S. Shin, J. Choi, K. L. Lee, J. Lee, S. Byun, S. Kim, H.-J. Lee et al., “Development of prediction models for screening depression and anxiety using smartphone and wearablebased digital phenotyping: protocol for the smartphone and wearable assessment for real-time screening of depression and anxiety (swarts-da) observational study in korea,” BMJ open, vol. 15, no. 6, p. e096773, 2025.
[9] A. Velu, J. Ramesh, A. Ahmed, S. Ganguly, R. Aburukba, A. Sagahyroon, and F. Aloul, “Integrating fitbit wearables and self-reported surveys for machine learning-based state–trait anxiety prediction,” Applied Sciences, vol. 15, no. 19, p. 10519, 2025.
[10] C. Nadal, C. Earley, A. Enrique, C. Sas, D. Richards, and G. Doherty, “Patient acceptance of selfmonitoring on a smartwatch in a routine digital therapy: a mixed-methods study,” ACM Transactions on Computer-Human Interaction, vol. 31, no. 1, pp. 1–50, 2023.
[11] D. S. S. Wuisan, R. A. Sunardjo, Q. Aini, N. A. Yusuf, and U. Rahardja, “Integrating artificial intelligence in human resource management: A smartpls approach for entrepreneurial success,” Aptisi Transactions on Technopreneurship (ATT), vol. 5, no. 3, pp. 334–345, 2023.
[12] E. Kalisperakis, T. Karantinos, M. Lazaridi, V. Garyfalli, P. P. Filntisis, A. Zlatintsi, N. Efthymiou, A. Mantas, L. Mantonakis, T. Mougiakos et al., “Smartwatch digital phenotypes predict positive and negative symptom variation in a longitudinal monitoring study of patients with psychotic disorders,” Frontiers in Psychiatry, vol. 14, p. 1024965, 2023.
[13] Y.-R. Lee and J.-S. Lee, “Real-time monitoring to predict depressive symptoms: study protocol,” Frontiers in Psychiatry, vol. 15, p. 1465933, 2025.
[14] E. Setiawaty, H. Hartoyo, R. Nurmalina, and L. N. Yuliati, “Entrepreneurship and innovation in telemedicine adoption among physicians in indonesia,” Aptisi Transactions on Technopreneurship (ATT), vol. 7, no. 3, pp. 927–941, 2025.
[15] S. Suminska and A. Rynkiewicz, “Mindfulness-based stress reduction training supplemented with physiological signals from smartwatch improves mindfulness and reduces stress, but not anxiety and depression,” Plos one, vol. 20, no. 4, p. e0322413, 2025.
[16] P. Lialiou and I. Maglogiannis, “Students’ burnout symptoms detection using smartwatch wearable devices: a systematic literature review,” AI Sensors, vol. 1, no. 1, p. 2, 2025.
[17] N. Lutfiani, D. A. Astrieta, V. Wildan, H. Sulistyaningrum, M. R. Anwar, and E. D. Astuti, “Emotional well-being and psychological support in infertility a multi-modal ai approach,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 5, no. 1, pp. 81–92, 2025.
[18] T. Robinson, J. Condell, E. Ramsey, and G. Leavey, “Self-management of subclinical common mental health disorders (anxiety, depression and sleep disorders) using wearable devices,” International journal of environmental research and public health, vol. 20, no. 3, p. 2636, 2023.
[19] N. K. Sahu, S. Gupta, and H. R. Lone, “Mad: A multimodal physiological and self-reported dataset for anxiety research from a low-to-middle-income country,” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 9, no. 4, pp. 1–34, 2025.
[20] K. V. Olesen, N. N. Lønfeldt, S. Das, A. K. Pagsberg, and L. K. H. Clemmensen, “Predicting obsessivecompulsive disorder events in children and adolescents in the wild using a wearable biosensor (wrist angel): Protocol for the analysis plan of a nonrandomized pilot study,” JMIR research protocols, vol. 12, no. 1, p. e48571, 2023.
[21] L. Meria, A. Andriyansah, F. Sutisna, A. William, and L. Pasha, “Unveiling the role of smartpls and technology in analyzing hr dynamics for organizational effectiveness,” International Journal of Cyber and IT Service Management (IJCITSM), vol. 5, no. 1, pp. 71–80, 2025.
[22] G. C. Malave, “Digital health and wearable technologies for the diagnosis and management of suicidality in adolescents and young adults: A scoping review,” Master’s thesis, College of Medicine-Mayo Clinic, 2023.
[23] L. Marciano, E. Vocaj, M. A. Bekalu, A. La Tona, G. Rocchi, and K. Viswanath, “The use of mobile assessments for monitoring mental health in youth: Umbrella review,” Journal of Medical Internet Research, vol. 25, p. e45540, 2023.
[24] J. L. Borelli, Y. Wang, F. H. Li, L. N. Russo, M. Tironi, K. Yamashita, E. Zhou, J. Lai, B. Nguyen, I. Azimi et al., “Detection of depressive symptoms in college students using multimodal passive sensing data and light gradient boosting machine: longitudinal pilot study,” JMIR Formative Research, vol. 9, no. 1, p. e67964, 2025.
[25] M. Choiri, E. S. Pramudito, F. Sutisna, and R. S. Sean, “Business artificial intelligence for enhancing sustainable decision intelligence,” IAIC Transactions on Sustainable Digital Innovation (ITSDI), vol. 7, no. 1, pp. 106–116, 2025.
[26] A. Sameh, L. Nauha, M. Seppanen, M. Niemel ¨ a, M. Oussalah, R. Korpelainen, and V. Farrahi, “Digital ¨ phenotyping using wearable-determined physical behaviors and machine learning to detect depression and anxiety in a general population,” medRxiv, pp. 2025–09, 2025.
[27] N. Kwon, D. Lee, S. Hwang, S. Yang, I. Youn, H.-J. Moon, and S. Han, “Enhancing the accuracy of mental health assessments through the integration of self-report and objective measures: A convergence study utilizing biosignals and 14-day wearable data,” Acta Psychologica, vol. 259, p. 105432, 2025.
[28] E. Erika, B. S. Riza, S. Maulana, and S. Rahagi, “Mapping the nexus of strategic management and sustainable development goals 12 with a focus on innovation: A bibliometric analysis,” IAIC Transactions on Sustainable Digital Innovation (ITSDI), vol. 7, no. 1, pp. 71–84, 2025.
[29] S. Yokoyama, F. Kagawa, M. Takamura, K. Takagaki, K. Kambara, Y. Mitsuyama, A. Shimizu, G. Okada, and Y. Okamoto, “Day-to-day regularity and diurnal switching of physical activity reduce depressionrelated behaviors: a time-series analysis of wearable device data,” BMC public health, vol. 23, no. 1, p. 34, 2023.
[30] A. Horwitz, E. Czyz, N. Al-Dajani, W. Dempsey, Z. Zhao, I. Nahum-Shani, and S. Sen, “Utilizing daily mood diaries and wearable sensor data to predict depression and suicidal ideation among medical interns,” Journal of affective disorders, vol. 313, pp. 1–7, 2022.
[31] H. W. Jung, D. Y. Kim, I. Lee, O. Kim, S. Lee, S. Lee, U. S. Chung, J.-H. Kim, S. Kim, J. W. Kim et al., “Key features of digital phenotyping for monitoring mental disorders: Systematic review,” Journal of Medical Internet Research, vol. 27, p. e77331, 2025.
[32] A. Williams, Y. Hasudungan, and N. Azizah, “The implementation of effective financial management to increase the profitability of startups,” Startupreneur Business Digital (SABDA Journal), vol. 4, no. 1, pp. 47–54, 2025.
[33] R. Tutunji, R. Proppert, C. Rieble, N. Jacobson, and E. Fried, “Integrating ecological momentary and passive sensing data to improve depression severity prediction: Insights from the warn-d study,” 2025.
[34] S. Fazeli, L. Levine, M. Beikzadeh, B. Mirzasoleiman, B. Zadeh, T. Peris, and M. Sarrafzadeh, “Passive monitoring of physiological precursors of stress leveraging smartwatch data,” in 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2022, pp. 2893–2899.
[35] B. Saylam and O. D. ¨ ˙Incel, “Multitask learning for mental health: depression, anxiety, stress (das) using wearables,” Diagnostics, vol. 14, no. 5, p. 501, 2024.
[36] Q. Aini, M. Hardini, A. Faturahman, D. Apriliasari, and A. C. Kiboy, “Analyzing user acceptance of ai based water quality monitoring through the utaut2 framework,” Sundara Advanced Research on Artificial Intelligence, vol. 1, no. 2, pp. 65–73, 2025.
[37] A. Arora, P. Chakraborty, and M. Bhatia, “Intervention of wearables and smartphones in real time monitoring of sleep and behavioral health: an assessment using adaptive neuro-fuzzy technique,” Arabian Journal for Science and Engineering, vol. 47, no. 2, pp. 1999–2024, 2022.
[38] R. V. Shah, G. Grennan, M. Zafar-Khan, F. Alim, S. Dey, D. Ramanathan, and J. Mishra, “Personalized machine learning of depressed mood using wearables,” Translational psychiatry, vol. 11, no. 1, p. 338, 2021.
[39] A. Abudaqa and I. Noburu, “Optimizing digipreneurship in the growth of the digital millennial creative economy ecosystem,” Startupreneur Business Digital (SABDA Journal), vol. 4, no. 1, pp. 24–34, 2025.
[40] A. Ahmed, S. Aziz, M. Alzubaidi, J. Schneider, S. Irshaidat, H. A. Serhan, A. A. Abd-Alrazaq, B. Solaiman, and M. Househ, “Wearable devices for anxiety & depression: A scoping review,” Computer Methods and Programs in Biomedicine Update, vol. 3, p. 100095, 2023.
[41] N. K. Sahu, S. Gupta, and H. Lone, “Wearable technology insights: Unveiling physiological responses during three different socially anxious activities,” ACM Journal on Computing and Sustainable Societies, vol. 2, no. 2, pp. 1–23, 2024.
[42] S. Jafarlou, I. Azimi, J. Lai, Y. Wang, S. Labbaf, B. Nguyen, H. Qureshi, C. Marcotullio, J. L. Borelli, N. D. Dutt et al., “Objective monitoring of loneliness levels using smart devices: A multi-device approach for mental health applications,” Plos one, vol. 19, no. 6, p. e0298949, 2024.
[43] Y.-B. Shin, A. Y. Kim, S. Kim, M.-S. Shin, J. Choi, K. L. Lee, J. Lee, S. Byun, S. Kim, and H.-J. Lee, “Development of Prediction Models for Screening Depression and Anxiety Using Smartphone and Wearable-Based Digital Phenotyping,” BMJ Open, vol. 15, no. 6, p. e096773, 2025.
[44] Y. Koh, C. Lee, E. Joung, H. Lee, and U. Lee, “Harnessing Home IoT for Self-Tracking Emotional WellBeing: Behavioral Patterns, Self-Reflection, and Privacy Concerns,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 9, no. 3, pp. 1–36, 2025.
[45] R. Amin, S. Schreynemackers, H. Oppenheimer, M. Petrovic, U. Hegerl, and H. Reich, “Mobile Sensing Data for Longitudinal Monitoring and Prediction of Depression Severity: A Systematic Review,” J Med Internet Res, vol. 27, p. e57418, 2025.
[46] E. A. Ankrah, F. L. Cibrian, L. M. Silva, A. Tavakoulnia, J. A. Beltran, S. E. B. Schuck, K. D. Lakes, and G. R. Hayes, “Me, My Health, and My Watch: How Children With ADHD Understand Smartwatch Health Data,” ACM Trans. Comput.-Hum. Interact., vol. 30, no. 4, pp. 1–25, 2023.
[47] M. M. Rahman, “Unlocking the Potential of Wearable Technology: Fitbit-Derived Measures for Predicting ADHD in Adolescents,” Front Child Adolesc Psychiatry, vol. 4, p. 1504323, 2025.
[48] D. Yamin, S. Lev-Ari, M. Mofaz, R. Elias, S. Toker, D. Spiegel, M. Yechezkel, M. L. Brandeau, and E. Shmueli, “Social Media Impact and Smartwatch Monitoring: Early Markers of PTSD and Anxiety Following Mass Traumatic Events,” PLOS Ment Health, vol. 2, no. 9, p. e0000195, 2025.
[49] J. Um, J. Park, D. E. Lee, J. E. Ahn, and J. H. Baek, “Machine Learning Models to Identify Imminent Suicide Risk Using Wearable Devices: A Pilot Study,” Psychiatry Investig, vol. 22, no. 2, p. 156, 2025.
[50] A. Abd-Alrazaq, R. AlSaad, S. Aziz, A. Ahmed, K. Denecke, M. Househ, F. Farooq, and J. Sheikh, “Wearable Artificial Intelligence for Anxiety and Depression: A Scoping Review,” J Med Internet Res, vol. 25, p. e42672, 2023.
[51] Y.-B. Shin, A. Y. Kim, S. Kim, M.-S. Shin, J. Choi, K. L. Lee, J. Lee, S. Byun, S. Kim, and H.-J. Lee, “Development of prediction models for screening depression and anxiety using smartphone and wearablebased digital phenotyping,” BMJ Open, vol. 15, no. 6, p. e096773, 2025.
[52] Y. Koh, C. Lee, E. Joung, H. Lee, and U. Lee, “Harnessing home iot for self-tracking emotional wellbeing: behavioral patterns and privacy concerns,” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 9, no. 3, pp. 1–36, 2025.
[53] R. Amin, S. Schreynemackers, H. Oppenheimer, M. Petrovic, U. Hegerl, and H. Reich, “Use of mobile sensing data for longitudinal monitoring and prediction of depression severity: systematic review,” Journal of Medical Internet Research, vol. 27, p. e57418, 2025.
[54] E. A. Ankrah, F. L. Cibrian, L. M. Silva, A. Tavakoulnia, J. A. Beltran, S. E. B. Schuck, K. D. Lakes, and G. R. Hayes, “How children with adhd interpret smartwatch health data,” ACM Transactions on Computer-Human Interaction, vol. 30, no. 4, pp. 1–25, 2023.
[55] A. Abd-Alrazaq, R. AlSaad, S. Aziz, A. Ahmed, K. Denecke, M. Househ, F. Farooq, and J. Sheikh, “Wearable artificial intelligence for anxiety and depression: scoping review,” Journal of Medical Internet Research, vol. 25, p. e42672, 2023.
[56] A. Choi, A. Ooi, and D. Lottridge, “Digital phenotyping for stress, anxiety, and mild depression: a systematic literature review,” JMIR mHealth and uHealth, vol. 12, no. 1, p. e40689, 2024.
[57] A. Kargarandehkordi, S. Li, K. Lin, K. T. Phillips, R. M. Benzo, and P. Washington, “Fusing wearable biosensors with artificial intelligence for mental health monitoring: a systematic review,” Biosensors, vol. 15, no. 4, p. 202, 2025.
[58] R. P. Hirten, M. Suprun, M. Danieletto, M. Zweig, E. Golden, R. Pyzik, S. Kaur, D. Helmus, A. Biello, and K. Landell, “Machine learning approach to determine resilience utilizing wearable device data,” JAMIA Open, vol. 6, no. 2, p. ooad029, 2023
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Po Abas Sunarya, Mohd Faiz Hilmi, Nesti Anggraini Santoso, Sondang Visiana Sihotang, Ramiro Santiago Ikhsan
This work is licensed under a Creative Commons Attribution 4.0 International License.
